© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23749
    Prev
    Next
    INDEX
    Explanations

    mentions of things being expensive

    oai_token-act-pair · gpt-3.5-turbo

    references to high costs or prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.80
    vironment
    -0.78
    oidal
    -0.76
    uberty
    -0.73
    ept
    -0.72
    İĭ
    -0.69
    swick
    -0.68
    obyl
    -0.67
    mbudsman
    -0.67
    sup
    -0.66
    POSITIVE LOGITS
     expensive
    1.14
     pricey
    0.98
     costly
    0.95
    liest
    0.88
     pric
    0.86
     prohib
    0.83
    expensive
    0.81
    lier
    0.81
    ly
    0.81
     ($
    0.80
    Activations Density 0.013%

    No Known Activations